From 19ffc7350636041025c6fe4553b35e3ed73f6d57 Mon Sep 17 00:00:00 2001
From: user name <ameynert@sdf-cs1.eidf.epcc.ed.ac.uk>
Date: Tue, 10 May 2022 09:58:23 +0100
Subject: [PATCH 1/2] Moved peddy validation checking script to bin
---
.../peddy_validation.pl | 2 +-
main.nf | 3 ---
pipeline/var_calling.nf | 14 +++++++-------
3 files changed, 8 insertions(+), 11 deletions(-)
rename trio_whole_exome_parse_peddy_ped_csv.pl => bin/peddy_validation.pl (98%)
mode change 100644 => 100755
diff --git a/trio_whole_exome_parse_peddy_ped_csv.pl b/bin/peddy_validation.pl
old mode 100644
new mode 100755
similarity index 98%
rename from trio_whole_exome_parse_peddy_ped_csv.pl
rename to bin/peddy_validation.pl
index 05e4d02..08cebeb
--- a/trio_whole_exome_parse_peddy_ped_csv.pl
+++ b/bin/peddy_validation.pl
@@ -2,7 +2,7 @@
=head1 NAME
-trio_whole_exome_parse_peddy_ped_csv.pl
+peddy_validation.pl
=head1 AUTHOR
diff --git a/main.nf b/main.nf
index 58404a7..91034a1 100644
--- a/main.nf
+++ b/main.nf
@@ -26,9 +26,6 @@ params.target_bed = null
// hg38 reference genome in fasta format
params.reference_genome = null
-// path to the parse_peddy_output Perl script. Todo: remove once scripts are in bin/
-params.parse_peddy_output = null
-
// path to a Ped file describing all the families in the pipeline batch
params.ped_file = null
diff --git a/pipeline/var_calling.nf b/pipeline/var_calling.nf
index 4ef7a4a..39ab013 100644
--- a/pipeline/var_calling.nf
+++ b/pipeline/var_calling.nf
@@ -176,7 +176,7 @@ process collate_pipeline_outputs {
path(ped_file)
path(samplesheet)
path(bcbio)
- path(parse_peddy_output)
+ path(peddy_validation_output)
output:
path("${params.pipeline_project_id}_${params.pipeline_project_version}")
@@ -204,8 +204,8 @@ process collate_pipeline_outputs {
--filename ${params.pipeline_project_id}_${params.pipeline_project_version}_qc_report.html \
. &&
- peddy_output=../qc/${params.pipeline_project_id}_${params.pipeline_project_version}.ped_check.txt &&
- perl ../../${parse_peddy_output} \
+ peddy_validation_output=../qc/${params.pipeline_project_id}_${params.pipeline_project_version}.ped_check.txt &&
+ peddy_validation.pl \
--output \$peddy_output \
--project ${params.pipeline_project_id} \
--batch ${bcbio_family_output_dirs[0].getName().split('_')[1]} \
@@ -214,10 +214,10 @@ process collate_pipeline_outputs {
--families . &&
# no && here - exit status checked below
- grep -v 'False\$' \$peddy_output
+ grep -v 'False\$' \$peddy_validation_output
if [ \$? -ne 0 ]
then
- echo "Found Peddy mismatches in \$peddy_output"
+ echo "Found Peddy mismatches in \$peddy_validation_output"
exit 1
fi &&
@@ -257,7 +257,7 @@ workflow process_families {
ch_bcbio = file(params.bcbio, checkIfExists: true)
ch_bcbio_template = file(params.bcbio_template, checkIfExists: true)
ch_target_bed = file(params.target_bed, checkIfExists: true)
- ch_parse_peddy_output = file(params.parse_peddy_output, checkIfExists: true)
+ ch_peddy_validation_output = file(params.peddy_validation_output, checkIfExists: true)
ch_reference_genome = file(params.reference_genome, checkIfExists: true)
ch_merged_fastqs = merge_fastqs(
@@ -317,7 +317,7 @@ workflow process_families {
ch_ped_file,
ch_samplesheet,
ch_bcbio,
- ch_parse_peddy_output
+ ch_peddy_validation_output
)
}
--
GitLab
From e2e492970ce5557d548ebf515e23def5a901fdaa Mon Sep 17 00:00:00 2001
From: user name <ameynert@sdf-cs1.eidf.epcc.ed.ac.uk>
Date: Tue, 10 May 2022 17:30:11 +0100
Subject: [PATCH 2/2] Pedigree checking setup
---
bin/peddy_validation.pl | 21 ++++++++++-----------
pipeline/var_calling.nf | 20 ++++++++------------
2 files changed, 18 insertions(+), 23 deletions(-)
diff --git a/bin/peddy_validation.pl b/bin/peddy_validation.pl
index 08cebeb..fe6507e 100755
--- a/bin/peddy_validation.pl
+++ b/bin/peddy_validation.pl
@@ -16,6 +16,7 @@ Checks the parent-child and parent-parent relationships from peddy output.
use strict;
+use Cwd;
use Getopt::Long;
use IO::File;
@@ -35,7 +36,6 @@ my $fam_dir;
my $project_id;
my $version;
my $out_file;
-my $batch_id;
GetOptions(
'help' => \$help,
@@ -43,11 +43,10 @@ GetOptions(
'ped=s' => \$ped_file,
'output=s' => \$out_file,
'families=s' => \$fam_dir,
- 'version=s' => \$version,
- 'batch=s' => \$batch_id
+ 'version=s' => \$version
) or die $usage;
-if ($help || !$project_id || !$ped_file || !$out_file || !$batch_id || !$version || !$fam_dir)
+if ($help || !$project_id || !$ped_file || !$out_file || !$version || !$fam_dir)
{
print $usage;
exit(0);
@@ -76,16 +75,16 @@ $in_fh->close();
my $out_fh = new IO::File;
$out_fh->open($out_file, "w") or die "Could not open $out_file\n$!";
-printf $out_fh "project_id\tbatch_id\tsample_a\tsample_b\tpedigree_parents\tpredicted_parents\tparent_error\n";
+printf $out_fh "project_id\tsample_a\tsample_b\tpedigree_parents\tpredicted_parents\tparent_error\n";
foreach my $family_id (sort keys %ped)
{
- my @peddy_glob = glob(sprintf("$fam_dir/*_%s_%s_%s_%s/%s_%s/qc/peddy/%s%s.ped_check.csv",
- $project_id, $version, $batch_id, $family_id, $ped{$family_id}{'aff'}, $family_id, $batch_id, $family_id));
- next if (scalar(@peddy_glob) == 0);
+ my $glob_str = sprintf("$fam_dir/*%s/%s/qc/peddy/*.ped_check.csv", $family_id, $ped{$family_id}{'aff'});
+ my @peddy_glob = glob($glob_str);
+ next if (scalar(@peddy_glob) == 0);
- my $peddy_fh = new IO::File;
- $peddy_fh->open($peddy_glob[0], "r") or die "Could not open $peddy_glob[0]\n$!";
+ my $peddy_fh = new IO::File;
+ $peddy_fh->open($peddy_glob[0], "r") or die "Could not open $peddy_glob[0]\n$!";
my @headers;
my %info;
@@ -129,7 +128,7 @@ foreach my $family_id (sort keys %ped)
$info{'parent_error'}{$sample_pair} = $info{'pedigree_parents'}{$sample_pair} eq $info{'predicted_parents'}{$sample_pair} ? 'False' : 'True';
- printf $out_fh "$project_id\t$batch_id\t$sample_pair\t%s\t%s\t%s\n",
+ printf $out_fh "$project_id\t$sample_pair\t%s\t%s\t%s\n",
$info{'pedigree_parents'}{$sample_pair},
$info{'predicted_parents'}{$sample_pair},
$info{'parent_error'}{$sample_pair};
diff --git a/pipeline/var_calling.nf b/pipeline/var_calling.nf
index 39ab013..a923477 100644
--- a/pipeline/var_calling.nf
+++ b/pipeline/var_calling.nf
@@ -176,7 +176,6 @@ process collate_pipeline_outputs {
path(ped_file)
path(samplesheet)
path(bcbio)
- path(peddy_validation_output)
output:
path("${params.pipeline_project_id}_${params.pipeline_project_version}")
@@ -206,20 +205,19 @@ process collate_pipeline_outputs {
peddy_validation_output=../qc/${params.pipeline_project_id}_${params.pipeline_project_version}.ped_check.txt &&
peddy_validation.pl \
- --output \$peddy_output \
+ --output \$peddy_validation_output \
--project ${params.pipeline_project_id} \
- --batch ${bcbio_family_output_dirs[0].getName().split('_')[1]} \
--version ${params.pipeline_project_version} \
--ped ../../${ped_file} \
--families . &&
# no && here - exit status checked below
- grep -v 'False\$' \$peddy_validation_output
- if [ \$? -ne 0 ]
- then
- echo "Found Peddy mismatches in \$peddy_validation_output"
- exit 1
- fi &&
+# grep -v 'False\$' \$peddy_validation_output
+# if [ \$? -ne 0 ]
+# then
+# echo "Found Peddy mismatches in \$peddy_validation_output"
+# exit 1
+# fi &&
cd ../.. &&
@@ -257,7 +255,6 @@ workflow process_families {
ch_bcbio = file(params.bcbio, checkIfExists: true)
ch_bcbio_template = file(params.bcbio_template, checkIfExists: true)
ch_target_bed = file(params.target_bed, checkIfExists: true)
- ch_peddy_validation_output = file(params.peddy_validation_output, checkIfExists: true)
ch_reference_genome = file(params.reference_genome, checkIfExists: true)
ch_merged_fastqs = merge_fastqs(
@@ -316,8 +313,7 @@ workflow process_families {
ch_formatted_bcbio_outputs.map({it[2]}).collect(),
ch_ped_file,
ch_samplesheet,
- ch_bcbio,
- ch_peddy_validation_output
+ ch_bcbio
)
}
--
GitLab